Release dates
— DeepSeek-R1 and its distilled models were released with open weights. ↗
DeepSeek-R1
Used large-scale reinforcement learning to shape reasoning and released both full and distilled model weights.
MODEL NUMBER026
- First public date
- 2025-01-20
- Organization
- DeepSeek
- Family
- DeepSeek V / R
01
Specifications
Only published specifications are shown.
- Total parameters
- 671B
- Active parameters
- 37B
- Architecture
- MoE
- Context
- 128,000 tokens
- Input modalities
- Text
- Open weights
- Yes
- License
- MIT
- Status
- Current
02
Overview
Why it mattered
R1 brought open-weight reasoning models into mainstream global comparison and accelerated replication of RL-based reasoning recipes.
03
Architecture & capabilities
Attention
MLA
Model capabilities
ReasoningCodingChain of thought
04
Release history
DeepSeek-R1 and its distilled models were released with open weights.
View sourceDeepSeek-R1-0528 launched with stronger reasoning, instruction following, and tool use.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.